© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121548
    Prev
    Next
    INDEX
    Explanations

    lib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,%
    -0.07
     >=
    -0.07
     th
    -0.06
    736
    -0.06
    By
    -0.06
    /'+
    -0.06
     Ign
    -0.06
    asdf
    -0.06
    (sprintf
    -0.06
     sized
    -0.06
    POSITIVE LOGITS
    lib
    0.09
     lib
    0.08
    /lib
    0.07
    AbsolutePath
    0.07
     accredited
    0.07
     sockfd
    0.07
    IBUTES
    0.07
     props
    0.07
    hz
    0.07
    plib
    0.07
    Activations Density 0.009%

    No Known Activations